serversdown
30185f3fd8
The MI50 box (CT202) runs an OpenAI-compatible llama.cpp server on 10.0.0.44:8080. Wire it in as a third backend: - llm.complete gains backend="mi50" (OpenAI client pointed at MI50_BASE_URL) - config: MI50_BASE_URL (default http://10.0.0.44:8080/v1) + MI50_MODEL - chat.respond labels the model per backend; web _backend_for maps "mi50" - UI backend selector adds "MI50 — local GPU" Verified end-to-end: llm.complete(backend="mi50") returns from the live server. See homelab-inference memory for the box topology. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
42 lines
1.4 KiB
Python
42 lines
1.4 KiB
Python
"""Environment-driven configuration."""
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class Config:
|
|
local_base_url: str
|
|
local_model: str
|
|
mi50_base_url: str # OpenAI-compatible llama.cpp server on the MI50 box
|
|
mi50_model: str
|
|
openai_api_key: str
|
|
cloud_model: str
|
|
embed_backend: str # "cloud" (OpenAI) or "local" (Ollama)
|
|
embed_model: str # OpenAI embedding model
|
|
local_embed_model: str # Ollama embedding model
|
|
summary_backend: str # "local" or "cloud" — backend used to compact memory
|
|
db_path: Path
|
|
|
|
|
|
def load() -> Config:
|
|
return Config(
|
|
local_base_url=os.getenv("LOCAL_BASE_URL", "http://localhost:11434"),
|
|
local_model=os.getenv("LOCAL_MODEL", "qwen2.5:7b-instruct"),
|
|
mi50_base_url=os.getenv("MI50_BASE_URL", "http://10.0.0.44:8080/v1"),
|
|
mi50_model=os.getenv("MI50_MODEL", "local-gpu"),
|
|
openai_api_key=os.getenv("OPENAI_API_KEY", ""),
|
|
cloud_model=os.getenv("CLOUD_MODEL", "gpt-4o-mini"),
|
|
embed_backend=os.getenv("EMBED_BACKEND", "cloud").lower(),
|
|
embed_model=os.getenv("EMBED_MODEL", "text-embedding-3-small"),
|
|
local_embed_model=os.getenv("LOCAL_EMBED_MODEL", "nomic-embed-text"),
|
|
summary_backend=os.getenv("SUMMARY_BACKEND", "local").lower(),
|
|
db_path=Path(os.getenv("LYRA_DB_PATH", "data/lyra.db")),
|
|
)
|